speakleash/Bielik-11B-v2.1-Instruct-GGUF-IQ-Imatrix
Quantization vs speakleash/Bielik-11B-v2.1-Instruct. speakleash/Bielik-11B-v2.1-Instruct-GGUF-IQ-Imatrix is a GGUF quantization (Q8_0) of the same weights: 101 tensors match exactly and 352 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/101, MLP 0/150, Attention 0/200, lm_head 0/1